Related papers: Applying Eigencontours to PolarMask-Based Instance…

Instance segmentation aims to detect and segment individual objects in a scene. Most existing methods rely on precise mask annotations of every category. However, it is difficult and costly to segment objects in novel categories because a…

We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is…

We propose Cut-Once-and-LEaRn (COLER), a simple approach for unsupervised instance segmentation and object detection. COLER first uses our developed CutOnce to generate coarse pseudo labels, then enables the detector to learn from these…

Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a…

Incorporating individual-level cognitive priors offers an important route to personalizing neural networks, yet accurately eliciting such priors remains challenging: existing methods either fail to uniquely identify them or introduce…

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…

In this paper, we focus on improving binary 2D instance segmentation to assist humans in labeling ground truth datasets with polygons. Humans labeler just have to draw boxes around objects, and polygons are generated automatically. To be…

Edge detection has long been an important problem in the field of computer vision. Previous works have explored category-agnostic or category-aware edge detection. In this paper, we explore edge detection in the context of object instances.…

Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance…

Polarimetric imaging enables advanced vision applications such as normal estimation and de-reflection by capturing unique surface-material interactions. However, existing applications (alternatively called downstream tasks) rely on datasets…

Many two-stage instance segmentation heads predict a coarse 28x28 mask per instance, which is insufficient to capture the fine-grained details of many objects. To address this issue, PointRend and RefineMask predict a 112x112 segmentation…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Translation of fully automated deep learning based medical image segmentation technologies to clinical workflows face two main algorithmic challenges. The first, is the collection and archival of large quantities of manually annotated…

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…

Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of…

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction…

Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. The real-time speed is very important for the autonomous vehicle algorithms along with the accuracy metric. In this paper, we propose a semi-supervised…

Contour-based instance segmentation methods include one-stage and multi-stage schemes. These approaches achieve remarkable performance. However, they have to define plenty of points to segment precise masks, which leads to high complexity.…

We present a method of cones for rigorous estimations of eigenvectors, eigenspaces and eigenvalues of a matrix. The key notion is the cone-domination and is inspired by ideas from hyperbolic dynamical systems. We present theorems which…